A framework for the evaluation of texture features with application to diagnostic ultrasound images

Author

Muzzolini, Russell ; Yang, Yee-Hong ; Pierson, Roger

Author_Institution

Saskatchewan Univ., Saskatoon, Sask., Canada

fYear

1991

fDate

2-9 Nov. 1991

Firstpage

2201

Abstract

A novel framework is presented to evaluate a given set of texture features, based on the set of textures they are to characterize. The textures are sampled from real images which are to be segmented, rather than the commonly used Brodatz textures. Using robust statistics, the number of outliers produced by each feature is used to determine its effectiveness in characterizing the set of textures. This framework is applied to a set of textures sampled from a sequence of diagnostic ultrasound images of an ovary in vitro. Thirty-two spatial and frequency domain texture features are evaluated.<>

Keywords

acoustic imaging; biomedical ultrasonics; medical image processing; texture; Brodatz textures; diagnostic ultrasound images; frequency domain; in vitro ovary; medical imaging; outliers; robust statistics; sampled textures; segmented images; spatial domain; texture features evaluation framework; Biomedical imaging; Computer vision; Councils; Frequency domain analysis; Gynaecology; Image segmentation; Partitioning algorithms; Robustness; Ultrasonic imaging; Ultrasonic variables measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Nuclear Science Symposium and Medical Imaging Conference, 1991., Conference Record of the 1991 IEEE

Conference_Location

Santa Fe, NM, USA

Print_ISBN

0-7803-0513-2

Type

conf

DOI

10.1109/NSSMIC.1991.259310

Filename

259310